Solve all disease. Developing and applying frontier AI to unlock deeper scientific insights, faster breakthroughs, and life-changing medicines.
- Tweets 305
- Following 84
- Followers 65,595
- Likes 33
Pinned Tweet
Empirical Methods → Exquisitely Engineered Molecules
How we make new medicines has evolved for centuries, but modern AI represents the biggest leap yet: moving from resource-intensive iterative design-make-test cycles to engineered precision.
Breakthroughs in frontier science rarely come from a sudden stroke of luck. Every major leap in AI drug design is the product of years of method development, rigorous engineering, and learning from what came before.
Witnessing the rapid advances in deep reinforcement learning and frontier AI capabilities led to a deep conviction: we could apply these same computational principles to other complex fields, like the engineering of new medicines.
That thinking led to the formation of Isomorphic Labs in 2021. Now, five years on, we have compelling evidence that our AI can unlock therapeutics to a wide range of disease classes. We are confident this technology will fundamentally impact how new medicines are created, from early discovery all the way through development.
In this article, I share the massive opportunity we have to transform human health with AI, and offer a look at the real, measurable progress we’re already making today.
isomorphiclabs.com/articles/…
2
15
154
19,537
Today, Isomorphic Labs joins the Virtual Biology Initiative (VBI) as a founding member.
We are helping build an open resource for the global research community to accelerate how we understand and treat disease.
Read more here: isomorphiclabs.com/articles/…
20
130
1,245
238,335
Previously, 85% of proteins associated with human disease were deemed intractable – their shapes and function made them less suitable for traditional chemical screening in the lab. Moving from experimental screening to AI generative design on a computer, we have seen these targets drastically open up the potential to design molecules with atomic precision, fundamentally expanding the number of diseases we can treat.
24
63
680
36,639
Over the last 50 years, computer-aided design has revolutionised almost every major engineering field – but its revolution in making medicines has only just begun.
Moving from manual execution to AI-driven design unlocks a depth and scale that was previously impossible. Our drug design engine, IsoDDE, intelligently searches vast chemical spaces to design functional molecules ready for the real world. What used to take months of lab work now happens computationally in just days.
The visualisation below is a representation of our drug design agent working autonomously over a 2-4 day period. Starting with a strict design specification (the biological target and desired molecular properties), our AI agent autonomously searches and iteratively generates new molecule designs that result in real world functional progress.
6
34
266
14,838
Empirical Methods → Exquisitely Engineered Molecules
How we make new medicines has evolved for centuries, but modern AI represents the biggest leap yet: moving from resource-intensive iterative design-make-test cycles to engineered precision.
Breakthroughs in frontier science rarely come from a sudden stroke of luck. Every major leap in AI drug design is the product of years of method development, rigorous engineering, and learning from what came before.
Witnessing the rapid advances in deep reinforcement learning and frontier AI capabilities led to a deep conviction: we could apply these same computational principles to other complex fields, like the engineering of new medicines.
That thinking led to the formation of Isomorphic Labs in 2021. Now, five years on, we have compelling evidence that our AI can unlock therapeutics to a wide range of disease classes. We are confident this technology will fundamentally impact how new medicines are created, from early discovery all the way through development.
In this article, I share the massive opportunity we have to transform human health with AI, and offer a look at the real, measurable progress we’re already making today.
isomorphiclabs.com/articles/…
2
15
154
19,537
Hear from AI expert and Isomorphic Labs President @maxjaderberg in his new blog, where he lays out what’s driving today’s breakthroughs in AI drug design and what the road ahead looks like.
isomorphiclabs.com/articles/…
1
13
1,329
From small molecules to complex biologics, the universe of potential medicines spanning multiple modalities is astronomically vast.
To put it in perspective: conservative estimates place the vast chemical search space for small, drug-like molecules near 10^60. The observable universe contains fewer stars – somewhere between 10^22 and 10^24. The answers to drug discovery’s toughest challenges exist within this vast space. And now, our drug design engine (IsoDDE) gives us the capability to navigate it.
13
71
694
70,552
Drug discovery is incredibly complex, but you don't need a background in biology to help solve it.
Hear from software engineer, Bartosz Bacewisz, on how transferable skills in tech and a shared motivation are helping us build frontier AI models to reimagine medicine.
bit.ly/424SMjZ
9
31
222
15,278
The prediction: 5 years for the industry to realise AI is essential in drug design and development – @maxjaderberg.
While this episode aired a year ago, we’ve been building for almost 5 years already, and have always held the conviction that our AI will redefine how new medicines are made.
6
23
336
21,387
Hear from John Strafford from Iso Business Development, on how combining Isomorphic Labs' capabilities with industry-leading partners sets us all up for success.
bit.ly/3RZJmor
4
2
41
10,835
Dr. Jennifer Doudna co-invented CRISPR and won the Nobel Prize for it. She also sits on our Scientific Advisory Board.
Jennifer recently spent the day with us, hosted by our Chief Research Officer, Sarah Skerratt. Moments like these sharpen our focus as we work towards building the future of medicine.
6
14
302
17,685
The heritage we were built on. Our Founder & CEO on cracking the code.
“Timing is very important. You need to pick hard problems to solve and be ambitious with them.”
Demis Hassabis discussed how his aspirations as a young gaming programmer were ahead of their time.
Watch our official interview: bit.ly/4jKV3Hh
ALT Demis Hassabis wears glasses, a dark suit, and blue tie, standing confidently against a dark blue background. Photo: Clément Morin.
5
8
126
21,260
Recognise this from our ICML talk?
Moore’s Law: Compute keeps getting cheaper. Eroom’s Law is the opposite - drug discovery keeps getting more expensive. At Iso, we’re using AI to change how drug design works - faster discovery timelines, and potential treatments reaching patients sooner.
9
13
115
11,815
"At ICML, Agnieszka Podsiadło and I are sharing some of what we're building at Isomorphic Labs: Methods that can generalise drug discovery - finding new biology, at scale and across pretty much every therapeutic modality. That last part matters to me most - it's how you get to a place where no patient is left behind." - Andreas Loukas, AI research scientist.
If you're in Seoul this week, come say hi to Andreas - @loukasa_tweet and the rest of our delegation at ICML.
3
16
150
17,642
Heading to @icmlconf? Isomorphic Labs’ hiring managers will be in Seoul from July 6–11 meeting with ML Engineers, ML Research Engineers and ML Research Scientists.
If you're ready to build frontier AI to tackle some of the biggest challenges in science, check the comments to meet our team.
5
3
106
16,512
The future of drug design relies on exceptional chemistry.
Heading to #EWOC Europe? The Isomorphic Labs team will be onsite and we're eager to meet with talented chemists and researchers. If you're interested in working at the intersection of frontier AI and chemistry to tackle some of the biggest challenges in science, come and talk to us about our open roles.
Register your interest in meeting up below!
3
2
41
6,690
"If you are keen to learn new stuff, you can come here and learn the most important things about the domain itself, on the job…"
Kuba Perlin, ML Staff Research Engineer, shares his insights into Iso's unique approach and explains why a formal science background isn't essential.
4
11
133
15,392
How do you design a molecule for a site you can't see? Eliza Strickland of @IEEESpectrum dives into our team’s efforts to predict ‘hidden’ binding sites and progress in structure prediction.
Read the article below:
Can AI move beyond predicting protein structures and start helping scientists discover entirely new ways to target disease? @IsomorphicLabs thinks so. spectrum.ieee.org/isomorphic…
6
2
71
13,068